详情

原文传递 Developing an Interactive Machine-Learning-based Approach for Sidewalk Digitalization.

题名：	Developing an Interactive Machine-Learning-based Approach for Sidewalk Digitalization.
作者：	Luo, J.; Wu, G.
关键词：	Sidewalk Digitalization, Interactive Machine-Learning, Fatal collisions
摘要：	In urban areas, many socio-economic concerns have been raised regarding fatal collisions, traffic congestion, and deteriorated air quality due to increased travel and logistic demands as well as the existing on-road transportation systems. As one of the promising remedies, active transportation has been advocated, which may not only mitigate congestion on local streets, but also promote physical fitness, foster community livability, and boost local economy (i). To promote the active transportation mode, extensive work has been focused on planning and developing a number of pedestrian and bicyclist related programs which require the infrastructure, e.g., sidewalks, as a premise (ii). A significant amount of these efforts have to go for the setup, maintenance and evaluation of the sidewalk inventory on a relatively large geographic scale (e.g., citywide, statewide), which lays a solid foundation for a variety of active-mobility-focused applications and related research. In the study, the authors propose to map the features of sidewalks based on the roadway network as the first step. The roadway network data applied in the study should include road link attributes and position coordinates, such as roadway shapefiles. Secondly, they will write a Python script to sweep each link in the initialized sidewalk network, bound a rectangular area which includes the link and extracts the aerial image within that area. In parallel, the authors will extract a large number of aerial images of sidewalk network, for example, ESRI ArcMap aerial basemaps, and set up a machine learning algorithm to learn from the labeled (‘paved’ and ‘not paved’) images. They will train the machine learning classifier to be able to predict a new sidewalk image at a reasonable prediction rate. Then the classifier can be used to predict the surface attributes of the extracted image using the trained machine learning algorithm.
报告类型：	科技报告